database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-06-30 21:42:05 +03:00
Code Activity

Improve support of Hunspell in ispell dictionary.

Browse Source 
Now it's possible to load recent version of Hunspell for several languages.
To handle these dictionaries Hunspell patch adds support for:
* FLAG long - sets the double extended ASCII character flag type
* FLAG num - sets the decimal number flag type (from 1 to 65535)
* AF parameter - alias for flag's set

Also it moves test dictionaries into separate directory.

Author: Artur Zakirov with editorization by me
This commit is contained in:
Teodor Sigaev
2016-03-04 20:08:10 +03:00
parent 9445db925e
commit d78a7d9c7f
15 changed files with 1105 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files

234
src/test/regress/expected/tsdicts.out
View File

@ -191,6 +191,198 @@ SELECT ts_lexize('hunspell', 'footballyklubber');
{foot,ball,klubber}
(1 row)
-- Test ISpell dictionary with hunspell affix file with FLAG long parameter
CREATE TEXT SEARCH DICTIONARY hunspell_long (
Template=ispell,
DictFile=hunspell_sample_long,
AffFile=hunspell_sample_long
);
SELECT ts_lexize('hunspell_long', 'skies');
ts_lexize
-----------
{sky}
(1 row)
SELECT ts_lexize('hunspell_long', 'bookings');
ts_lexize
----------------
{booking,book}
(1 row)
SELECT ts_lexize('hunspell_long', 'booking');
ts_lexize
----------------
{booking,book}
(1 row)
SELECT ts_lexize('hunspell_long', 'foot');
ts_lexize
-----------
{foot}
(1 row)
SELECT ts_lexize('hunspell_long', 'foots');
ts_lexize
-----------
{foot}
(1 row)
SELECT ts_lexize('hunspell_long', 'rebookings');
ts_lexize
----------------
{booking,book}
(1 row)
SELECT ts_lexize('hunspell_long', 'rebooking');
ts_lexize
----------------
{booking,book}
(1 row)
SELECT ts_lexize('hunspell_long', 'rebook');
ts_lexize
-----------
(1 row)
SELECT ts_lexize('hunspell_long', 'unbookings');
ts_lexize
-----------
{book}
(1 row)
SELECT ts_lexize('hunspell_long', 'unbooking');
ts_lexize
-----------
{book}
(1 row)
SELECT ts_lexize('hunspell_long', 'unbook');
ts_lexize
-----------
{book}
(1 row)
SELECT ts_lexize('hunspell_long', 'footklubber');
ts_lexize
----------------
{foot,klubber}
(1 row)
SELECT ts_lexize('hunspell_long', 'footballklubber');
ts_lexize
------------------------------------------------------
{footballklubber,foot,ball,klubber,football,klubber}
(1 row)
SELECT ts_lexize('hunspell_long', 'ballyklubber');
ts_lexize
----------------
{ball,klubber}
(1 row)
SELECT ts_lexize('hunspell_long', 'footballyklubber');
ts_lexize
---------------------
{foot,ball,klubber}
(1 row)
-- Test ISpell dictionary with hunspell affix file with FLAG num parameter
CREATE TEXT SEARCH DICTIONARY hunspell_num (
Template=ispell,
DictFile=hunspell_sample_num,
AffFile=hunspell_sample_num
);
SELECT ts_lexize('hunspell_num', 'skies');
ts_lexize
-----------
{sky}
(1 row)
SELECT ts_lexize('hunspell_num', 'bookings');
ts_lexize
----------------
{booking,book}
(1 row)
SELECT ts_lexize('hunspell_num', 'booking');
ts_lexize
----------------
{booking,book}
(1 row)
SELECT ts_lexize('hunspell_num', 'foot');
ts_lexize
-----------
{foot}
(1 row)
SELECT ts_lexize('hunspell_num', 'foots');
ts_lexize
-----------
{foot}
(1 row)
SELECT ts_lexize('hunspell_num', 'rebookings');
ts_lexize
----------------
{booking,book}
(1 row)
SELECT ts_lexize('hunspell_num', 'rebooking');
ts_lexize
----------------
{booking,book}
(1 row)
SELECT ts_lexize('hunspell_num', 'rebook');
ts_lexize
-----------
(1 row)
SELECT ts_lexize('hunspell_num', 'unbookings');
ts_lexize
-----------
{book}
(1 row)
SELECT ts_lexize('hunspell_num', 'unbooking');
ts_lexize
-----------
{book}
(1 row)
SELECT ts_lexize('hunspell_num', 'unbook');
ts_lexize
-----------
{book}
(1 row)
SELECT ts_lexize('hunspell_num', 'footklubber');
ts_lexize
----------------
{foot,klubber}
(1 row)
SELECT ts_lexize('hunspell_num', 'footballklubber');
ts_lexize
------------------------------------------------------
{footballklubber,foot,ball,klubber,football,klubber}
(1 row)
SELECT ts_lexize('hunspell_num', 'ballyklubber');
ts_lexize
----------------
{ball,klubber}
(1 row)
SELECT ts_lexize('hunspell_num', 'footballyklubber');
ts_lexize
---------------------
{foot,ball,klubber}
(1 row)
-- Synonim dictionary
CREATE TEXT SEARCH DICTIONARY synonym (
Template=synonym,
@ -277,6 +469,48 @@ SELECT to_tsquery('hunspell_tst', 'footballyklubber:b & rebookings:A & sky');
'foot':B & 'ball':B & 'klubber':B & ( 'booking':A | 'book':A ) & 'sky'
(1 row)
-- Test ispell dictionary with hunspell affix with FLAG long in configuration
ALTER TEXT SEARCH CONFIGURATION hunspell_tst ALTER MAPPING
REPLACE hunspell WITH hunspell_long;
SELECT to_tsvector('hunspell_tst', 'Booking the skies after rebookings for footballklubber from a foot');
to_tsvector
----------------------------------------------------------------------------------------------------
'ball':7 'book':1,5 'booking':1,5 'foot':7,10 'football':7 'footballklubber':7 'klubber':7 'sky':3
(1 row)
SELECT to_tsquery('hunspell_tst', 'footballklubber');
to_tsquery
------------------------------------------------------------------------------
( 'footballklubber' | 'foot' & 'ball' & 'klubber' ) | 'football' & 'klubber'
(1 row)
SELECT to_tsquery('hunspell_tst', 'footballyklubber:b & rebookings:A & sky');
to_tsquery
------------------------------------------------------------------------
'foot':B & 'ball':B & 'klubber':B & ( 'booking':A | 'book':A ) & 'sky'
(1 row)
-- Test ispell dictionary with hunspell affix with FLAG num in configuration
ALTER TEXT SEARCH CONFIGURATION hunspell_tst ALTER MAPPING
REPLACE hunspell_long WITH hunspell_num;
SELECT to_tsvector('hunspell_tst', 'Booking the skies after rebookings for footballklubber from a foot');
to_tsvector
----------------------------------------------------------------------------------------------------
'ball':7 'book':1,5 'booking':1,5 'foot':7,10 'football':7 'footballklubber':7 'klubber':7 'sky':3
(1 row)
SELECT to_tsquery('hunspell_tst', 'footballklubber');
to_tsquery
------------------------------------------------------------------------------
( 'footballklubber' | 'foot' & 'ball' & 'klubber' ) | 'football' & 'klubber'
(1 row)
SELECT to_tsquery('hunspell_tst', 'footballyklubber:b & rebookings:A & sky');
to_tsquery
------------------------------------------------------------------------
'foot':B & 'ball':B & 'klubber':B & ( 'booking':A | 'book':A ) & 'sky'
(1 row)
-- Test synonym dictionary in configuration
CREATE TEXT SEARCH CONFIGURATION synonym_tst (
COPY=english

64
src/test/regress/sql/tsdicts.sql
View File

@ -48,6 +48,54 @@ SELECT ts_lexize('hunspell', 'footballklubber');
SELECT ts_lexize('hunspell', 'ballyklubber');
SELECT ts_lexize('hunspell', 'footballyklubber');
-- Test ISpell dictionary with hunspell affix file with FLAG long parameter
CREATE TEXT SEARCH DICTIONARY hunspell_long (
Template=ispell,
DictFile=hunspell_sample_long,
AffFile=hunspell_sample_long
);
SELECT ts_lexize('hunspell_long', 'skies');
SELECT ts_lexize('hunspell_long', 'bookings');
SELECT ts_lexize('hunspell_long', 'booking');
SELECT ts_lexize('hunspell_long', 'foot');
SELECT ts_lexize('hunspell_long', 'foots');
SELECT ts_lexize('hunspell_long', 'rebookings');
SELECT ts_lexize('hunspell_long', 'rebooking');
SELECT ts_lexize('hunspell_long', 'rebook');
SELECT ts_lexize('hunspell_long', 'unbookings');
SELECT ts_lexize('hunspell_long', 'unbooking');
SELECT ts_lexize('hunspell_long', 'unbook');
SELECT ts_lexize('hunspell_long', 'footklubber');
SELECT ts_lexize('hunspell_long', 'footballklubber');
SELECT ts_lexize('hunspell_long', 'ballyklubber');
SELECT ts_lexize('hunspell_long', 'footballyklubber');
-- Test ISpell dictionary with hunspell affix file with FLAG num parameter
CREATE TEXT SEARCH DICTIONARY hunspell_num (
Template=ispell,
DictFile=hunspell_sample_num,
AffFile=hunspell_sample_num
);
SELECT ts_lexize('hunspell_num', 'skies');
SELECT ts_lexize('hunspell_num', 'bookings');
SELECT ts_lexize('hunspell_num', 'booking');
SELECT ts_lexize('hunspell_num', 'foot');
SELECT ts_lexize('hunspell_num', 'foots');
SELECT ts_lexize('hunspell_num', 'rebookings');
SELECT ts_lexize('hunspell_num', 'rebooking');
SELECT ts_lexize('hunspell_num', 'rebook');
SELECT ts_lexize('hunspell_num', 'unbookings');
SELECT ts_lexize('hunspell_num', 'unbooking');
SELECT ts_lexize('hunspell_num', 'unbook');
SELECT ts_lexize('hunspell_num', 'footklubber');
SELECT ts_lexize('hunspell_num', 'footballklubber');
SELECT ts_lexize('hunspell_num', 'ballyklubber');
SELECT ts_lexize('hunspell_num', 'footballyklubber');
-- Synonim dictionary
CREATE TEXT SEARCH DICTIONARY synonym (
Template=synonym,
@ -94,6 +142,22 @@ SELECT to_tsvector('hunspell_tst', 'Booking the skies after rebookings for footb
SELECT to_tsquery('hunspell_tst', 'footballklubber');
SELECT to_tsquery('hunspell_tst', 'footballyklubber:b & rebookings:A & sky');
-- Test ispell dictionary with hunspell affix with FLAG long in configuration
ALTER TEXT SEARCH CONFIGURATION hunspell_tst ALTER MAPPING
REPLACE hunspell WITH hunspell_long;
SELECT to_tsvector('hunspell_tst', 'Booking the skies after rebookings for footballklubber from a foot');
SELECT to_tsquery('hunspell_tst', 'footballklubber');
SELECT to_tsquery('hunspell_tst', 'footballyklubber:b & rebookings:A & sky');
-- Test ispell dictionary with hunspell affix with FLAG num in configuration
ALTER TEXT SEARCH CONFIGURATION hunspell_tst ALTER MAPPING
REPLACE hunspell_long WITH hunspell_num;
SELECT to_tsvector('hunspell_tst', 'Booking the skies after rebookings for footballklubber from a foot');
SELECT to_tsquery('hunspell_tst', 'footballklubber');
SELECT to_tsquery('hunspell_tst', 'footballyklubber:b & rebookings:A & sky');
-- Test synonym dictionary in configuration
CREATE TEXT SEARCH CONFIGURATION synonym_tst (
COPY=english